| 1. |
- Camerer, C. F., et al.
(författare)
-
Evaluating the replicability of social science experiments in Nature and Science between 2010 and 2015
- 2018
-
Ingår i: Nature Human Behaviour. - : Springer Science and Business Media LLC. - 2397-3374. ; 2:9, s. 637-644
-
Tidskriftsartikel (refereegranskat)abstract
- Being able to replicate scientific findings is crucial for scientific progress1-15. We replicate 21 systematically selected experimental studies in the social sciences published in Nature and Science between 2010 and 201516-36. The replications follow analysis plans reviewed by the original authors and pre-registered prior to the replications. The replications are high powered, with sample sizes on average about five times higher than in the original studies. We find a significant effect in the same direction as the original study for 13 (62%) studies, and the effect size of the replications is on average about 50% of the original effect size. Replicability varies between 12 (57%) and 14 (67%) studies for complementary replicability indicators. Consistent with these results, the estimated truepositive rate is 67% in a Bayesian analysis. The relative effect size of true positives is estimated to be 71%, suggesting that both false positives and inflated effect sizes of true positives contribute to imperfect reproducibility. Furthermore, we find that peer beliefs of replicability are strongly related to replicability, suggesting that the research community could predict which results would replicate and that failures to replicate were not the result of chance alone.
|
|
| 2. |
- Altmejd, Adam
(författare)
-
Education & replication : essays on the determinants of college choice and the predictability of lab replications
- 2018
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- This Ph.D. thesis is a collection of three research articles.In "Sibling Influence on College Choice" the author studies how preferences for university schooling are affected by the education experience of siblings. An individual is considerably more likely to apply to a specific program if their sibling studies it. The effect is driven by siblings having a preference for going to the same institution. It is twice as strong when both siblings are male, but does not change with neither parental education nor the popularity of the program. A possible explanation is that siblings follow each other out of convenience."Relative Returns to Swedish College Fields" is a paper about the economic returns to different college orientations. Even though Sweden has the lowest average college premium in the developed world, differences between fields can be large. Medicine and engineering have returns of over $10,000 per year compared to other fields. Humanities, on the other hand, has a large enough negative payoff that the degree holder likely earns less than those who do not go to university at all. Interestingly, applicants do not seem to care much about low returns when chosing what to study, but instead prioritize non-pucuniary benefits of college education."Predicting Replication" covers a completely different topic. In the paper, the author team design a simple machine learning algorithmic that predicts the outcomes of laboratory experiment replications in Psychology and Economics. The model is very accurate, on par with the forecasts of experts. It could be used to make better decisions about which studies to replicate, and thus increase cost-effectiveness of replication efforts.
|
|
